| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 24.0, | |
| "eval_steps": 500, | |
| "global_step": 72, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.6283529996871948, | |
| "eval_runtime": 3.1863, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.4084081649780273, | |
| "eval_runtime": 3.1869, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.2192631959915161, | |
| "eval_runtime": 3.1877, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.43165192008018494, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4843, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.040535569190979, | |
| "eval_runtime": 3.1877, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.8558390736579895, | |
| "eval_runtime": 3.187, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.6931569576263428, | |
| "eval_runtime": 3.1865, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.8776572942733765, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7175, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.5830169916152954, | |
| "eval_runtime": 3.1867, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.49080416560173035, | |
| "eval_runtime": 3.1854, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.48263129591941833, | |
| "eval_runtime": 3.1874, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.8698680996894836, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1599, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.470937579870224, | |
| "eval_runtime": 3.1861, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.4739013612270355, | |
| "eval_runtime": 3.1862, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.4649692475795746, | |
| "eval_runtime": 3.1861, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.4578638970851898, | |
| "eval_runtime": 3.1863, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 0.8457691669464111, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0259, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.4607035219669342, | |
| "eval_runtime": 3.186, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.45176398754119873, | |
| "eval_runtime": 3.1856, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.4511236846446991, | |
| "eval_runtime": 3.1849, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 16.666666666666668, | |
| "grad_norm": 0.5995622277259827, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0099, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.43412062525749207, | |
| "eval_runtime": 3.1865, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.43398618698120117, | |
| "eval_runtime": 3.1863, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.43465808033943176, | |
| "eval_runtime": 3.1849, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.09180915355682373, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0031, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.43288353085517883, | |
| "eval_runtime": 3.187, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.43253418803215027, | |
| "eval_runtime": 3.186, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.44188740849494934, | |
| "eval_runtime": 3.1856, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.43514636158943176, | |
| "eval_runtime": 3.1859, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 23.333333333333332, | |
| "grad_norm": 0.010112113319337368, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0031, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.43539562821388245, | |
| "eval_runtime": 3.1858, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 72 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 180, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 60, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7412512567853056.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |